Method for processing the output of a speech recognizer

Abstract

A method for processing speech, comprising semantically parsing a received natural language speech input with respect to a plurality of predetermined command grammars in an automated speech processing system; determining if the parsed speech input unambiguously corresponds to a command and is sufficiently complete for reliable processing, then processing the command; if the speech input ambiguously corresponds to a single command or is not sufficiently complete for reliable processing, then prompting a user for further speech input to reduce ambiguity or increase completeness, in dependence on a relationship of previously received speech input and at least one command grammar of the plurality of predetermined command grammars, reparsing the further speech input in conjunction with previously parsed speech input, and iterating as necessary. The system also monitors abort, fail or cancel conditions in the speech input.

What is claimed is: 
     
       1. A speech processing system, comprising: a command dictionary embodied in a network; an input configured to receive a speech signal;
 at least one processor configured to: 
 determine a context of the speech processing system; 
 determine a set of command grammars from the command dictionary consistent with the determined context; 
 parse the received speech signal according to linguistic models of the determined set of contextually-consistent command grammars; 
 determine a completeness of the parsed received speech signal according to the linguistic models of the determined set of contextually-consistent command grammars; and 
 generate a command execution signal dependent on the determination of completeness; and 
 an output configured to communicate the generated command execution signal. 
 
     
     
       2. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to generate a prompt for information to resolve an incompleteness of the parsed received speech signal according to the linguistic models of the determined set of contextually-consistent command grammars. 
     
     
       3. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to detect a command activation statement in the received speech signal, and to parse the speech signal received after the command activation statement. 
     
     
       4. The speech processing system according to  claim 3 , wherein the at least one processor is further configured to change the context of the speech processing system dependent on the command activation statement. 
     
     
       5. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to concurrently parse the received speech signal according to linguistic models of a plurality of contextually-consistent command grammars. 
     
     
       6. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to determine if a command is successfully processed. 
     
     
       7. The speech processing system according to  claim 6 , wherein the at least one processor is further configured to contingently process a subsequent received speech signal dependent on whether the command is successfully processed. 
     
     
       8. The speech processing system according to  claim 6 , wherein the at least one processor is further configured to process at least a portion of the received speech signal in a dictation mode, substantially without parsing signal according to the linguistic models of the determined set of contextually-consistent command grammars. 
     
     
       9. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to control a graphic user interface dependent on the received speech signal. 
     
     
       10. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to generate a textual representation of the received speech signal. 
     
     
       11. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to parse the received speech signal according to a natural language model. 
     
     
       12. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to parse the received speech signal according to a syntactic analysis process. 
     
     
       13. The speech processing system according to  claim 1 , wherein the at least one processor is further configured to determine a statistical reliability of a correspondence of the received speech signal to a command grammar. 
     
     
       14. A speech processing method, comprising:
 receiving a speech signal; 
 determining a context of the received speech signal; 
 determining a set of command grammars from a command dictionary embodied in a network consistent with the determined context; 
 parsing the received speech signal according to linguistic models of the determined set of contextually-consistent command grammars with at least one automated processor; 
 determining a completeness of the parsed received speech signal according to the linguistic models of the determined set of contextually-consistent command grammars with the at least one processor; and 
 generating a command execution signal dependent on the determination of completeness. 
 
     
     
       15. The method according to  claim 14 , further comprising generating a prompt for information to resolve an incompleteness of the parsed received speech signal according to the linguistic models of the determined set of contextually-consistent command grammars. 
     
     
       16. The method according to  claim 14 , further comprising detecting a command activation statement in the received speech signal, and parsing the speech signal received after the command activation statement. 
     
     
       17. The method according to  claim 16 , further comprising changing the context dependent on the command activation statement. 
     
     
       18. The method according to  claim 14 , further comprising concurrently parsing the received speech signal according to linguistic models of a plurality of contextually-consistent command grammars. 
     
     
       19. The method according to  claim 14 , further comprising controlling a graphic user interface dependent on the received speech signal. 
     
     
       20. A speech processing method, comprising:
 determining a context-dependent set of command grammars from a command dictionary embodied in a data matrix or network; 
 automatically parsing a received speech signal according to at least one linguistic model of the determined set of context-dependent command grammars; 
 automatically determining a command represented in the parsed received speech signal according to the at least one linguistic model of the determined set of context-dependent command grammars and automatic execution of completeness logic and disambiguation logic; and 
 automatically generating and conveying a command execution signal selectively dependent on the determined command.